[NV] [PR3] feat(dsv4): enable synthetic acceptance for DSV4 FP4 GB200 MTP2 / [NV] [PR3] feat(dsv4)：为 DSV4 FP4 GB200 MTP2 启用合成接受率

Enable selected synthetic-acceptance Pareto points and a matching baseline with aligned NIXL and router metadata. / 启用选定的合成接受率 Pareto 配置及对应基线，并保持 NIXL 与路由器元数据一致。

Author: qiching

configs/nvidia-master.yaml

@@ -5220,6 +5220,99 @@ dsv4-fp4-gb200-dynamo-vllm-mtp2:
   kv-p2p-transfer: nixl
   multinode: true
   disagg: true
+  scenarios:
+    fixed-seq-len:
+    - isl: 8192
+      osl: 1024
+      search-space:
+      # Aggregate low latency: TP=8, max-num-seqs=4.
+      - conc-list: [1]
+        spec-decoding: mtp
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 1
+          dp-attn: false
+          additional-settings:
+          - "SYNTHETIC_ACCEPTANCE=true"
+          - "SYNTHETIC_ACCEPTANCE_LENGTH=2.27"
+          - "CONFIG_FILE=recipes/vllm/deepseek-v4/8k1k/agg-gb200-low-latency-mtp2.yaml"
+        decode:
+          num-worker: 0
+          tp: 8
+          ep: 1
+          dp-attn: false
+
+      # Low-latency bridge: 1 prefill (DEP=8) + 4 decode (TP=8), no offload.
+      - conc-list: [16, 32, 64]
+        spec-decoding: mtp
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "SYNTHETIC_ACCEPTANCE=true"
+          - "SYNTHETIC_ACCEPTANCE_LENGTH=2.27"
+          - "CONFIG_FILE=recipes/vllm/deepseek-v4/8k1k/disagg-gb200-low-latency-mtp2.yaml"
+        decode:
+          num-worker: 4
+          tp: 8
+          ep: 1
+          dp-attn: false
+
+      # MegaMOE mid curve: 1 prefill (DEP=8) + 1 decode (DEP=8).
+      # 5 nodes total with a dedicated NATS/etcd infra node.
+      - conc-list: [128, 256, 512, 1024]
+        spec-decoding: mtp
+        prefill:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "SYNTHETIC_ACCEPTANCE=true"
+          - "SYNTHETIC_ACCEPTANCE_LENGTH=2.27"
+          - "CONFIG_FILE=recipes/vllm/deepseek-v4/8k1k/disagg-gb200-mid-curve-megamoe-mtp2.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+
+      # MegaMOE high throughput: 2 prefill (DEP=8 each) + 1 decode (DEP=8).
+      # 7 nodes total with a dedicated NATS/etcd infra node.
+      - conc-list: [1024]
+        spec-decoding: mtp
+        prefill:
+          num-worker: 2
+          tp: 8
+          ep: 8
+          dp-attn: true
+          additional-settings:
+          - "SYNTHETIC_ACCEPTANCE=true"
+          - "SYNTHETIC_ACCEPTANCE_LENGTH=2.27"
+          - "CONFIG_FILE=recipes/vllm/deepseek-v4/8k1k/disagg-gb200-high-tpt-megamoe-mtp2.yaml"
+        decode:
+          num-worker: 1
+          tp: 8
+          ep: 8
+          dp-attn: true
+
+# Baseline (no synthetic acceptance) variant of dsv4-fp4-gb200-dynamo-vllm-mtp2
+# for before/after Pareto comparison. Identical topology and recipes, only the
+# SYNTHETIC_ACCEPTANCE envs are removed.
+dsv4-fp4-gb200-dynamo-vllm-mtp2-nosynthetic:
+  image: vllm/vllm-openai:v0.20.1-ubuntu2404
+  model: deepseek-ai/DeepSeek-V4-Pro
+  model-prefix: dsv4
+  runner: gb200
+  precision: fp4
+  framework: dynamo-vllm
+  router: { name: dynamo-router, version: "1.2.0.dev20260426" }
+  multinode: true
+  disagg: true
+  kv-p2p-transfer: nixl
   scenarios:
     fixed-seq-len:
     - isl: 8192